EMAE — Estimador Mensual de Actividad Económica

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds real value with the INDEC_API_TOKEN authentication requirement and the default-latest-month behavior, but it says nothing about response shape, pagination mechanics, or rate limits, and there is no output schema to compensate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the dataset identity and base year, then the two modes, then the default and auth requirement. Telegraphic phrasing is dense but every clause carries information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, zero-required read tool with no output schema, the description covers the essentials: dataset vintage, the two access modes, default behavior, and credentials. Remaining gaps — pagination flow and return-field listing — are partly handled by the offset and columnas schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 91%, so the baseline would be 3, but the description genuinely adds meaning: it explains that nivel selects between two different result sets and which series each contains, and clarifies the variación semantics (monthly/interannual depending on series). The desde/hasta default behavior is echoed rather than extended, keeping it from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names the specific dataset (EMAE, base 2004=100) and states exactly what each mode returns: nivel='general' gives serie original, desestacionalizada and tendencia-ciclo with índice and variaciones, while nivel='sectores' gives activity-sector series. This lets an agent distinguish it from dataset-generic siblings like indec_query_dataset, though it never explicitly says to prefer this tool over those.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete operating conditions: which nivel values exist and what each contains, that omitting desde/hasta returns only the latest month, and that an API token is required. It stops short of explicit when-to-use vs alternatives (e.g., versus indec_query_dataset or indec_ipi), so routing between siblings remains inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.